ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 MemBox: Shared Memory Device for Memory-Centric Computing Applicable to Deep Learning Problems
Cited 0 time in scopus Download 10 time Share share facebook twitter linkedin kakaostory
저자
최용석, 임은지, 신재권, 이철훈
발행일
202111
출처
Electronics, v.10 no.21, pp.1-18
ISSN
2079-9292
출판사
MDPI
DOI
https://dx.doi.org/10.3390/electronics10212720
협약과제
21HS3300, 메모리 중심 차세대 컴퓨팅 시스템 구조 연구, 김강호
초록
Large-scale computational problems that need to be addressed in modern computers, such as deep learning or big data analysis, cannot be solved in a single computer, but can be solved with distributed computer systems. Since most distributed computing systems, consisting of a large number of networked computers, should propagate their computational results to each other, they can suffer the problem of an increasing overhead, resulting in lower computational efficiencies. To solve these problems, we proposed an architecture of a distributed system that used a shared memory that is simultaneously accessible by multiple computers. Our architecture aimed to be implemented in FPGA or ASIC. Using an FPGA board that implemented our architecture, we configured the actual distributed system and showed the feasibility of our system. We compared the results of the deep learning application test using our architecture with that using Google Tensorflow's parameter server mechanism. We showed improvements in our architecture beyond Google Tensorflow's parameter server mechanism and we determined the future direction of research by deriving the expected problems.
키워드
ASIC, Big data, Deep learning, Distributed system, FPGA, Shared memory
KSP 제안 키워드
Big Data analysis, Deep learning application, Distributed System(DS), Distributed computing systems, FPGA Board, Google TensorFlow, Parameter server, Shared Memory, computational problems, computational results, deep learning(DL)
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)